eb5618911a
- Enable the per-vcpu dirty-ring tracking mechanism, together with an option to keep the good old dirty log around for pages that are dirtied by something other than a vcpu. - Switch to the relaxed parallel fault handling, using RCU to delay page table reclaim and giving better performance under load. - Relax the MTE ABI, allowing a VMM to use the MAP_SHARED mapping option, which multi-process VMMs such as crosvm rely on. - Merge the pKVM shadow vcpu state tracking that allows the hypervisor to have its own view of a vcpu, keeping that state private. - Add support for the PMUv3p5 architecture revision, bringing support for 64bit counters on systems that support it, and fix the no-quite-compliant CHAIN-ed counter support for the machines that actually exist out there. - Fix a handful of minor issues around 52bit VA/PA support (64kB pages only) as a prefix of the oncoming support for 4kB and 16kB pages. - Add/Enable/Fix a bunch of selftests covering memslots, breakpoints, stage-2 faults and access tracking. You name it, we got it, we probably broke it. - Pick a small set of documentation and spelling fixes, because no good merge window would be complete without those. As a side effect, this tag also drags: - The 'kvmarm-fixes-6.1-3' tag as a dependency to the dirty-ring series - A shared branch with the arm64 tree that repaints all the system registers to match the ARM ARM's naming, and resulting in interesting conflicts -----BEGIN PGP SIGNATURE----- iQJDBAABCgAtFiEEn9UcU+C1Yxj9lZw9I9DQutE9ekMFAmOODb0PHG1hekBrZXJu ZWwub3JnAAoJECPQ0LrRPXpDztsQAInRnsgLl57/SpqhZzExNCllN6AT/bdeB3uz rnw3ScJOV174uNKp8lnPWoTvu2YUGiVtBp6tFHhDI8le7zHX438ZT8KE5mcs8p5i KfFKnb8SHV2DDpqkcy24c0Xl/6vsg1qkKrdfJb49yl5ZakRITDpynW/7tn6dXsxX wASeGFdCYeW4g2xMQzsCbtx6LgeQ8uomBmzRfPrOtZHYYxAn6+4Mj4595EC1sWxM AQnbp8tW3Vw46saEZAQvUEOGOW9q0Nls7G21YqQ52IA+ZVDK1LmAF2b1XY3edjkk pX8EsXOURfqdasBxfSfF3SgnUazoz9GHpSzp1cTVTktrPp40rrT7Ldtml0ktq69d 1malPj47KVMDsIq0kNJGnMxciXFgAHw+VaCQX+k4zhIatNwviMbSop2fEoxj22jc 4YGgGOxaGrnvmAJhreCIbr4CkZk5CJ8Zvmtfg+QM6npIp8BY8896nvORx/d4i6tT H4caadd8AAR56ANUyd3+KqF3x0WrkaU0PLHJLy1tKwOXJUUTjcpvIfahBAAeUlSR qEFrtb+EEMPgAwLfNOICcNkPZR/yyuYvM+FiUQNVy5cNiwFkpztpIctfOFaHySGF K07O2/a1F6xKL0OKRUg7hGKknF9ecmux4vHhiUMuIk9VOgNTWobHozBDorLKXMzC aWa6oGVC =iIPT -----END PGP SIGNATURE----- Merge tag 'kvmarm-6.2' of https://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD KVM/arm64 updates for 6.2 - Enable the per-vcpu dirty-ring tracking mechanism, together with an option to keep the good old dirty log around for pages that are dirtied by something other than a vcpu. - Switch to the relaxed parallel fault handling, using RCU to delay page table reclaim and giving better performance under load. - Relax the MTE ABI, allowing a VMM to use the MAP_SHARED mapping option, which multi-process VMMs such as crosvm rely on. - Merge the pKVM shadow vcpu state tracking that allows the hypervisor to have its own view of a vcpu, keeping that state private. - Add support for the PMUv3p5 architecture revision, bringing support for 64bit counters on systems that support it, and fix the no-quite-compliant CHAIN-ed counter support for the machines that actually exist out there. - Fix a handful of minor issues around 52bit VA/PA support (64kB pages only) as a prefix of the oncoming support for 4kB and 16kB pages. - Add/Enable/Fix a bunch of selftests covering memslots, breakpoints, stage-2 faults and access tracking. You name it, we got it, we probably broke it. - Pick a small set of documentation and spelling fixes, because no good merge window would be complete without those. As a side effect, this tag also drags: - The 'kvmarm-fixes-6.1-3' tag as a dependency to the dirty-ring series - A shared branch with the arm64 tree that repaints all the system registers to match the ARM ARM's naming, and resulting in interesting conflicts
183 lines
4.4 KiB
C
183 lines
4.4 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* KVM memslot modification stress test
|
|
* Adapted from demand_paging_test.c
|
|
*
|
|
* Copyright (C) 2018, Red Hat, Inc.
|
|
* Copyright (C) 2020, Google, Inc.
|
|
*/
|
|
|
|
#define _GNU_SOURCE /* for program_invocation_name */
|
|
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <sys/syscall.h>
|
|
#include <unistd.h>
|
|
#include <asm/unistd.h>
|
|
#include <time.h>
|
|
#include <poll.h>
|
|
#include <pthread.h>
|
|
#include <linux/bitmap.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/userfaultfd.h>
|
|
|
|
#include "memstress.h"
|
|
#include "processor.h"
|
|
#include "test_util.h"
|
|
#include "guest_modes.h"
|
|
|
|
#define DUMMY_MEMSLOT_INDEX 7
|
|
|
|
#define DEFAULT_MEMSLOT_MODIFICATION_ITERATIONS 10
|
|
|
|
|
|
static int nr_vcpus = 1;
|
|
static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
|
|
|
|
static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
|
|
{
|
|
struct kvm_vcpu *vcpu = vcpu_args->vcpu;
|
|
struct kvm_run *run;
|
|
int ret;
|
|
|
|
run = vcpu->run;
|
|
|
|
/* Let the guest access its memory until a stop signal is received */
|
|
while (!READ_ONCE(memstress_args.stop_vcpus)) {
|
|
ret = _vcpu_run(vcpu);
|
|
TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
|
|
|
|
if (get_ucall(vcpu, NULL) == UCALL_SYNC)
|
|
continue;
|
|
|
|
TEST_ASSERT(false,
|
|
"Invalid guest sync status: exit_reason=%s\n",
|
|
exit_reason_str(run->exit_reason));
|
|
}
|
|
}
|
|
|
|
struct memslot_antagonist_args {
|
|
struct kvm_vm *vm;
|
|
useconds_t delay;
|
|
uint64_t nr_modifications;
|
|
};
|
|
|
|
static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay,
|
|
uint64_t nr_modifications)
|
|
{
|
|
uint64_t pages = max_t(int, vm->page_size, getpagesize()) / vm->page_size;
|
|
uint64_t gpa;
|
|
int i;
|
|
|
|
/*
|
|
* Add the dummy memslot just below the memstress memslot, which is
|
|
* at the top of the guest physical address space.
|
|
*/
|
|
gpa = memstress_args.gpa - pages * vm->page_size;
|
|
|
|
for (i = 0; i < nr_modifications; i++) {
|
|
usleep(delay);
|
|
vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa,
|
|
DUMMY_MEMSLOT_INDEX, pages, 0);
|
|
|
|
vm_mem_region_delete(vm, DUMMY_MEMSLOT_INDEX);
|
|
}
|
|
}
|
|
|
|
struct test_params {
|
|
useconds_t delay;
|
|
uint64_t nr_iterations;
|
|
bool partition_vcpu_memory_access;
|
|
};
|
|
|
|
static void run_test(enum vm_guest_mode mode, void *arg)
|
|
{
|
|
struct test_params *p = arg;
|
|
struct kvm_vm *vm;
|
|
|
|
vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
|
|
VM_MEM_SRC_ANONYMOUS,
|
|
p->partition_vcpu_memory_access);
|
|
|
|
pr_info("Finished creating vCPUs\n");
|
|
|
|
memstress_start_vcpu_threads(nr_vcpus, vcpu_worker);
|
|
|
|
pr_info("Started all vCPUs\n");
|
|
|
|
add_remove_memslot(vm, p->delay, p->nr_iterations);
|
|
|
|
memstress_join_vcpu_threads(nr_vcpus);
|
|
pr_info("All vCPU threads joined\n");
|
|
|
|
memstress_destroy_vm(vm);
|
|
}
|
|
|
|
static void help(char *name)
|
|
{
|
|
puts("");
|
|
printf("usage: %s [-h] [-m mode] [-d delay_usec]\n"
|
|
" [-b memory] [-v vcpus] [-o] [-i iterations]\n", name);
|
|
guest_modes_help();
|
|
printf(" -d: add a delay between each iteration of adding and\n"
|
|
" deleting a memslot in usec.\n");
|
|
printf(" -b: specify the size of the memory region which should be\n"
|
|
" accessed by each vCPU. e.g. 10M or 3G.\n"
|
|
" Default: 1G\n");
|
|
printf(" -v: specify the number of vCPUs to run.\n");
|
|
printf(" -o: Overlap guest memory accesses instead of partitioning\n"
|
|
" them into a separate region of memory for each vCPU.\n");
|
|
printf(" -i: specify the number of iterations of adding and removing\n"
|
|
" a memslot.\n"
|
|
" Default: %d\n", DEFAULT_MEMSLOT_MODIFICATION_ITERATIONS);
|
|
puts("");
|
|
exit(0);
|
|
}
|
|
|
|
int main(int argc, char *argv[])
|
|
{
|
|
int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
|
|
int opt;
|
|
struct test_params p = {
|
|
.delay = 0,
|
|
.nr_iterations = DEFAULT_MEMSLOT_MODIFICATION_ITERATIONS,
|
|
.partition_vcpu_memory_access = true
|
|
};
|
|
|
|
guest_modes_append_default();
|
|
|
|
while ((opt = getopt(argc, argv, "hm:d:b:v:oi:")) != -1) {
|
|
switch (opt) {
|
|
case 'm':
|
|
guest_modes_cmdline(optarg);
|
|
break;
|
|
case 'd':
|
|
p.delay = atoi_non_negative("Delay", optarg);
|
|
break;
|
|
case 'b':
|
|
guest_percpu_mem_size = parse_size(optarg);
|
|
break;
|
|
case 'v':
|
|
nr_vcpus = atoi_positive("Number of vCPUs", optarg);
|
|
TEST_ASSERT(nr_vcpus <= max_vcpus,
|
|
"Invalid number of vcpus, must be between 1 and %d",
|
|
max_vcpus);
|
|
break;
|
|
case 'o':
|
|
p.partition_vcpu_memory_access = false;
|
|
break;
|
|
case 'i':
|
|
p.nr_iterations = atoi_positive("Number of iterations", optarg);
|
|
break;
|
|
case 'h':
|
|
default:
|
|
help(argv[0]);
|
|
break;
|
|
}
|
|
}
|
|
|
|
for_each_guest_mode(run_test, &p);
|
|
|
|
return 0;
|
|
}
|